Text-Guided Feature Mining for Fine-Grained Ship Classification in Optical Remote Sensing Images

Ship classification in remote sensing images holds paramount significance for surveillance and defense applications. However, the intricate nature of ship classes poses a challenge in accurately discriminating among diverse ship types. This challenge is exacerbated by the long-tailed data distribution, where certain classes are underrepresented by insufficient samples. Furthermore, the limited visual information available from single-perspective remote sensing imaging complicates the extraction of discriminative features. To address these challenges, we propose the Text-Guided Feature Mining Network (TGFMN). This approach aims to exploit strong textual knowledge to construct discriminative image features. We employ a unified classifier for pre-training to classify features from both modalities, ensuring that the dual modal features are integrated into a cohesive feature space, thereby maximizing the efficacy of textual information. The text-guided strategy is employed to enhance attention regions within the shallow spatial dimensions of visual features, facilitating the extraction of highly discriminative visual features during the fine-tuning process. The experimental results demonstrate the effectiveness of our method, achieving state-of-the-art performance on two benchmark datasets for fine-grained ship classification in remote sensing: FGSC-23 and FGSCR-42.